Power your agent
The publisher's own command. Not a PlugMCP endpoint.
Host a copy with our keys and logs.
uvx toon-parse-mcp==1.0.4-betaClaude Code has no install link for a local command. Copy the command below and run it in a terminal.
claude mcp add io.github.ankitpal181-toon-parse-mcp -- uvx toon-parse-mcp==1.0.4-betaRun in a terminal.
{ "mcpServers": { "io.github.ankitpal181-toon-parse-mcp": { "command": "uvx", "args": [ "toon-parse-mcp==1.0.4-beta" ] } }}claude_desktop_config.json
Remote URL or a command on your machine? How the two installs differ
Run on PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
LaunchFrom the publisher
mcp-name: io.github.ankitpal181/toon-parse-mcp
A specialized Model Context Protocol (MCP) server that optimizes token usage by converting data to TOON (Token-Oriented Object Notation) and stripping non-essential context from code files.
MCP server that reduces LLM context by removing code comments and converting data formats to TOON
The toon-parse-mcp MCP server helps AI agents (like Cursor, Claude Desktop, etc.) operate more efficiently by:
optimize_input_context(raw_input: str): Processes raw text data (JSON/XML/CSV/YAML) and returns optimized TOON format.read_and_optimize_file(file_path: str): Reads a local code file and returns a token-optimized version (no inline comments, minimized whitespace).protocol://mandatory-efficiency: Provides a strict system instruction prompt for LLMs to ensure they use the optimization tools correctly.pip install toon-parse-mcp
toon-parse-mcpcommandpython3 -m toon_parse_mcp.server (Ensure your environment is active or use absolute path to python)~/.codeium/windsurf/mcp_config.json directly.mcpServers object:{
"mcpServers": {
"toon-parse-mcp": {
"command": "python3",
"args": ["-m", "toon_parse_mcp.server"]
}
}
}
~/.gemini/antigravity/mcp_config.json directly.mcpServers object:{
"mcpServers": {
"toon-parse-mcp": {
"command": "python3",
"args": ["-m", "toon_parse_mcp.server"]
}
}
}
Add this to your claude_desktop_config.json:
{
"mcpServers": {
"toon-parse-mcp": {
"command": "python3",
"args": ["-m", "toon_parse_mcp.server"]
}
}
}
When the server is active, the AI will have access to the optimize_input_context and read_and_optimize_file tools. You can also refer to the efficiency protocol by asking the AI to "check the mandatory efficiency protocol".
To run the test suite:
pip install -e ".[test]"
pytest tests/
mcp >= 1.25.0toon-parse >= 2.4.3MIT License - see LICENSE for details.
© 2026 MCP Directory.
MCP server that reduces LLM context by removing code comments and converting data formats to TOON
{ "mcpServers": { "io.github.ankitpal181-toon-parse-mcp": { "command": "uvx", "args": [ "toon-parse-mcp==1.0.4-beta" ] } }}Tools
No tool list yet. Remote servers get one after the first health check.
FAQ
Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.
No required environment variable is listed on this record.
Toon Parse runs locally over stdio.
Last checked 2026-11-09. MCP server that reduces LLM context by removing code comments and converting data formats to TOON